Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/dryvist/claude-code-plugins/codeql-generic-resolvergit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00016 | $0.01726 |
| Opus 5 | $0.00008 | $0.00863 |
| Sonnet 5 | $0.00003 | $0.00345 |
| Haiku 4.5 | $0.00002 | $0.00173 |
Grade B, and why
CodeQL Generic Resolver scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post("https://api.example.com", auth=("user", "password123")) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post("https://api.example.com", auth=("user", "password123")) How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeQL Generic Resolver
Handle CodeQL alerts that don't fit the permissions or expression injection categories by analyzing, attempting common fixes, and escalating unclear cases.
Input
{
"alerts": [
{
"number": 25,
"rule": "py/hardcoded-credential",
"location": "scripts/deploy.py",
"line_number": 42,
"message": "Password is hardcoded here"
}
]
}
Supported Alert Types
| Category | Rules | Common Fix |
|---|---|---|
| Hardcoded Credentials | py/hardcoded-credential, js/hardcoded-credential, etc. |
Move to GitHub Secrets, use env vars |
| Resource Leaks | py/resource-not-closed, js/uncaught-promise, etc. |
Add cleanup/finally blocks |
| Path Traversal | py/sql-injection, js/path-traversal, etc. |
Validate input, use safe APIs |
| Unsafe Shell | py/unsafe-shell, bash/dangerous-pipe, etc. |
Use set -euo pipefail, quote vars |
| Other | Any unlisted rule | Escalate for human review |
Workflow per Alert
1. Parse Alert
Extract:
- Rule ID/category
- File location
- Line number and context
- Alert message (contains fix hint)
2. Categorize & Match Pattern
Compare rule against known patterns:
rule_id:
py/hardcoded-credential
js/hardcoded-credential
→ CATEGORY: Hardcoded Credentials
rule_id:
py/sql-injection
java/sql-injection
→ CATEGORY: Input Validation
rule_id:
(anything else)
→ CATEGORY: Other / Escalate
3. Attempt Fix (if Pattern Matches)
Pattern A: Hardcoded Credentials
File: scripts/deploy.py:42
api_key = "sk-abc123def456" # ALERT: Hardcoded credential
Fix:
-
Move to GitHub Secrets (or environment variable)
-
Update code to read from env:
api_key = os.environ.get("API_KEY") -
Add to workflow using
secrets.API_KEY
Decision: If this is a script outside workflows, escalate to human (can't auto-add to workflow). If in workflow, apply fix.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 292 lines · 16 tokens per session scan B 11cbe4445e1d
CodeQL Generic Resolver is an agent published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 1,726 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
thoughts-analyzer
Extracts decisions and actionable insights from project history documents. Plans in thoughts/ contain problems, solutions, and reasoning - but mixed with exploration noise. Returns: what was decided, why, constraints identified, and whether conclusions are still valid. Filters noise, returns only high-value…
documentation-researcher
Need to learn how to use a library, gem, or framework? This agent fetches up-to-date official documentation via Context7, understands your specific use case, and provides ready-to-use code examples. Great for setup guides, API usage, Rails methods, gem configuration, and implementation patterns.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.
review-tests-minitest
Minitest test quality and coverage reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-tests-minitest in repos that test with minitest. Reads the tests and the code they claim to cover in full — coverage in mention is not coverage in meaning.
review-docs
Documentation reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-docs with artifact paths. Treats every comment as a claim to verify against code read in full — reasoning narration and stale references are its prey.
review-performance
Performance reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-performance with artifact paths. Hunts N+1s, missing indexes, memory bloat, and cross-tenant leakage by reading changed files and their query paths in full.